Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106155
    Prev
    Next
    INDEX
    Explanations

    functions and API responses related to user authentication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipheral
    -0.07
     Temper
    -0.06
    ickle
    -0.06
    sei
    -0.06
    Bearer
    -0.06
    praak
    -0.06
    ież
    -0.06
    ieten
    -0.06
    cies
    -0.06
    alars
    -0.06
    POSITIVE LOGITS
     login
    0.10
    .login
    0.10
    login
    0.08
     Ker
    0.08
    /login
    0.08
     Login
    0.07
     ker
    0.07
    (login
    0.07
    .Login
    0.07
    Forg
    0.07
    Activations Density 0.046%

    No Known Activations